Nondestructive Detection of Blueberry Fruit Fly Pests Based on Deep Learning and Hyperspectral Imaging

被引：0

作者：

Tian Y. ^{[1
,2
]}

Wu W. ^{[1
]}

Lin L. ^{[1
,2
]}

Jiang F. ^{[1
,2
]}

Zhang F. ^{[1
]}

机构：

[1] College of Information and Electrical Engineering, Shenyang Agriculural University, Shenyang

[2] Key Laboratory of Horticultural Equipment, Ministry of Agriculture and Rural Affairs, Shenyang

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2023年 / 54卷 / 01期

关键词：

blueberry fruit fly pests; hyperspectral imaging; im-ResNet50; model; nondestructive detection;

D O I：

10.6041/j.issn.1000-1298.2023.01.040

中图分类号：

学科分类号：

摘要：

Aiming at the problems of low efficiency and poor accuracy in the classification and recognition of blueberry fruit fly pests, a deep learning method was proposed to process and analyze the collected blueberry hyperspectral images, so as to realize the nondestructive detection of blueberry fruit fly pests. Firstly, the dimension of blueberry hyperspectral image was reduced by PCA. And the better data set PC2 and PC3 was selected. The best data set PC23 was obtained by splicing PC2 and PC3. The seven enhancement operations were performed on the images in the dataset, including 90° rotation, 180° rotation, blur, brightness adjustment, mirror image and Gaussian noise, so as to expand the capacity of each data set to 18 times of the original capacity. Then the three deep learning models of VGG16, InceptionV3 and ResNet50 were used to recognize and detect blueberry fruit fly pest images, and high recognition accuracy was achieved. Among them, ResNet50 model had the highest efficiency, and the accuracy of ResNet50 model was the highest, reaching 92.92%, and the loss rate was the lowest, only 3.08%. Therefore, ResNet50 model had the best overall recognition effect on the nondestructive detection of blueberry fruit fly pests. Finally, an improved im-ResNet50 model was constructed based on ResNet50 model from three aspects: ECA attention module, Focal Loss loss function and Mish activation function. The recognition accuracy of im-ResNet50 model was 95.69%, and the loss rate was reduced to 1.52%. The results showed that im-ResNet50 model effectively improved the pest identification ability of blueberry fruit fly. The interpretability of im-ResNet50 model was also analyzed by Grad-CAM. The research results can quickly and accurately detect the blueberry fruit fly pests, and it can provide theoretical support for the intelligent detection and online sorting of small berry quality. © 2023 Chinese Society of Agricultural Machinery. All rights reserved.

引用

页码：393 / 401

页数：8

共 28 条

[1] QIAO S, TIAN Y W, WANG Q, Et al., Nondestructive detection of decayed blueberry based on information fusion of hyperspectral imaging ( HSI) and low-field nuclear magnetic resonance ( LF - NMR) [J], Computers and Electronics in Agriculture, 184, (2021)
[2] SHEN Jianwei, LI Lin, WEI Xinhua, Design of intelligent irrigation decision system for blueberry garden in hilly area [ J ], Transactions of the Chinese Society for Agricultural Machinery, 49, pp. 379-386, (2018)
[3] ZHANG Xiaoyan, ZHENG Shan, XIE Lixue, Et al., A report on insect infestation and disease on blueberry bushes in Fujian [ J ], Fujian Journal of Agricultural Sciences, 34, 3, pp. 338-343, (2019)
[4] CHANDRASEKARAN I, PANIGRAHI S S, RAVIKANTH L, Et al., Potential of near-infrared ( NIR) spectroscopy and hyperspectral imaging for quality and safety assessment of fruits , an overview [ J ], Food Analytical Methods, 12, pp. 2438-2458, (2019)
[5] XING J, GUYER D, ARIANA D, Et al., Determining optimal wavebands using genetic algorithm for detection of internal insect infestation in tart cherry [ J ], Sensing and Instrumentation for Food Quality and Safety, 2, 3, pp. 161-167, (2008)
[6] HAFF R P, SARANWONG S, THANAPASE W, Et al., Automatic image analysis and spot classification for detection of fruit fly infestation in hyperspectral images of mangoes, Postharvest Biology & Technology, 86, pp. 23-28, (2013)
[7] WANG Shuaishuai, Feature vectors selection for fresh peach pest detection based on hyperspectral imaging [ J ], Journal of Xinyang Agriculture and Forestry University, 25, 4, pp. 119-123, (2015)
[8] LIU Dehua, ZHANG Shujuan, WANG Bin, Et al., Detection of hawthorn fruit defects using hyperspectral imaging [ J ], Spectroscopy and Spectral Analysis, 35, 11, pp. 3167-3171, (2015)
[9] AGARWAL M, AL-SHUWAILI T, NUGALIYADDE A, Et al., Identification and diagnosis of whole body and fragments of Trogoderma granarium and Trogoderma variabile using visible near infrared hyperspectral imaging technique coupled with deep learning[ J], Computers and Electronics in Agriculture, 173, (2020)
[10] HAN Z Z, GAO J Y., Pixel-level aflatoxin detecting based on deep learning and hyperspectral imaging [ J ], Computers and Electronics in Agriculture, 164, (2019)

← 1 2 3 →